© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20562
    Prev
    Next
    INDEX
    Explanations

    apprehension and apprehension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acterísticas
    -2.75
     saluti
    -2.67
     proib
    -2.63
     ladri
    -2.61
     prega
    -2.53
    ]
    -2.48
     auguri
    -2.42
     dà
    -2.41
     rende
    -2.41
    และ
    -2.39
    POSITIVE LOGITS
    ↵
    2.67
     ziemlich
    2.33
     apprehension
    2.28
     outcry
    2.25
     związane
    2.17
     articulate
    2.16
    虽说
    2.11
     "[
    2.05
    それとも
    2.02
     creciente
    2.00
    Activations Density 0.000%

    No Known Activations